| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.016022620169651, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03770028275212064, | |
| "grad_norm": 2.8582637310028076, | |
| "learning_rate": 4.9995083170283816e-05, | |
| "loss": 2.995, | |
| "num_input_tokens_seen": 57008, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07540056550424128, | |
| "grad_norm": 2.4749696254730225, | |
| "learning_rate": 4.998033461515242e-05, | |
| "loss": 2.7127, | |
| "num_input_tokens_seen": 117936, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11310084825636192, | |
| "grad_norm": 2.3738160133361816, | |
| "learning_rate": 4.9955760135896534e-05, | |
| "loss": 2.6302, | |
| "num_input_tokens_seen": 176288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15080113100848255, | |
| "grad_norm": 2.2132370471954346, | |
| "learning_rate": 4.992136939879856e-05, | |
| "loss": 2.5818, | |
| "num_input_tokens_seen": 229712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1885014137606032, | |
| "grad_norm": 2.444084882736206, | |
| "learning_rate": 4.9877175931330346e-05, | |
| "loss": 2.4913, | |
| "num_input_tokens_seen": 288784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22620169651272384, | |
| "grad_norm": 2.190948009490967, | |
| "learning_rate": 4.982319711683221e-05, | |
| "loss": 2.4694, | |
| "num_input_tokens_seen": 347712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2639019792648445, | |
| "grad_norm": 1.9827752113342285, | |
| "learning_rate": 4.975945418767529e-05, | |
| "loss": 2.4525, | |
| "num_input_tokens_seen": 404272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3016022620169651, | |
| "grad_norm": 2.3744397163391113, | |
| "learning_rate": 4.968597221690986e-05, | |
| "loss": 2.4745, | |
| "num_input_tokens_seen": 461632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3393025447690858, | |
| "grad_norm": 2.5817763805389404, | |
| "learning_rate": 4.96027801084029e-05, | |
| "loss": 2.4637, | |
| "num_input_tokens_seen": 518016, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3770028275212064, | |
| "grad_norm": 2.2218539714813232, | |
| "learning_rate": 4.950991058546893e-05, | |
| "loss": 2.5011, | |
| "num_input_tokens_seen": 579312, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41470311027332707, | |
| "grad_norm": 2.5139260292053223, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 2.4397, | |
| "num_input_tokens_seen": 636448, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4524033930254477, | |
| "grad_norm": 2.589820623397827, | |
| "learning_rate": 4.929528920808854e-05, | |
| "loss": 2.4109, | |
| "num_input_tokens_seen": 693504, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49010367577756836, | |
| "grad_norm": 2.8880276679992676, | |
| "learning_rate": 4.917362177418342e-05, | |
| "loss": 2.4228, | |
| "num_input_tokens_seen": 752160, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.527803958529689, | |
| "grad_norm": 2.480609178543091, | |
| "learning_rate": 4.904244573372733e-05, | |
| "loss": 2.4391, | |
| "num_input_tokens_seen": 811296, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5655042412818096, | |
| "grad_norm": 2.6764094829559326, | |
| "learning_rate": 4.8901812684340564e-05, | |
| "loss": 2.4552, | |
| "num_input_tokens_seen": 867696, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6032045240339302, | |
| "grad_norm": 2.666821002960205, | |
| "learning_rate": 4.8751777943523634e-05, | |
| "loss": 2.3658, | |
| "num_input_tokens_seen": 924944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6409048067860509, | |
| "grad_norm": 2.884999990463257, | |
| "learning_rate": 4.8592400526898314e-05, | |
| "loss": 2.359, | |
| "num_input_tokens_seen": 978768, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6786050895381716, | |
| "grad_norm": 2.58659291267395, | |
| "learning_rate": 4.842374312499405e-05, | |
| "loss": 2.4228, | |
| "num_input_tokens_seen": 1034544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7163053722902922, | |
| "grad_norm": 2.6272594928741455, | |
| "learning_rate": 4.824587207858888e-05, | |
| "loss": 2.32, | |
| "num_input_tokens_seen": 1091776, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7540056550424128, | |
| "grad_norm": 2.6761183738708496, | |
| "learning_rate": 4.805885735261454e-05, | |
| "loss": 2.3393, | |
| "num_input_tokens_seen": 1153056, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7917059377945335, | |
| "grad_norm": 2.721721887588501, | |
| "learning_rate": 4.786277250863599e-05, | |
| "loss": 2.2595, | |
| "num_input_tokens_seen": 1211808, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8294062205466541, | |
| "grad_norm": 2.718644618988037, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 2.3171, | |
| "num_input_tokens_seen": 1273600, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8671065032987747, | |
| "grad_norm": 2.6614394187927246, | |
| "learning_rate": 4.744370452107789e-05, | |
| "loss": 2.2949, | |
| "num_input_tokens_seen": 1331392, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9048067860508954, | |
| "grad_norm": 2.851165771484375, | |
| "learning_rate": 4.722088621637309e-05, | |
| "loss": 2.3818, | |
| "num_input_tokens_seen": 1387664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.942507068803016, | |
| "grad_norm": 2.692765235900879, | |
| "learning_rate": 4.698932740657479e-05, | |
| "loss": 2.2494, | |
| "num_input_tokens_seen": 1445968, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9802073515551367, | |
| "grad_norm": 2.7365992069244385, | |
| "learning_rate": 4.6749119174501975e-05, | |
| "loss": 2.3593, | |
| "num_input_tokens_seen": 1497744, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0179076343072573, | |
| "grad_norm": 2.6355655193328857, | |
| "learning_rate": 4.6500356005192514e-05, | |
| "loss": 2.1892, | |
| "num_input_tokens_seen": 1549008, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.055607917059378, | |
| "grad_norm": 2.8112802505493164, | |
| "learning_rate": 4.6243135748737864e-05, | |
| "loss": 2.1753, | |
| "num_input_tokens_seen": 1605152, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0933081998114986, | |
| "grad_norm": 3.1792027950286865, | |
| "learning_rate": 4.597755958179406e-05, | |
| "loss": 2.1186, | |
| "num_input_tokens_seen": 1663456, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.1310084825636193, | |
| "grad_norm": 3.5244438648223877, | |
| "learning_rate": 4.570373196778427e-05, | |
| "loss": 2.0526, | |
| "num_input_tokens_seen": 1722320, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1687087653157398, | |
| "grad_norm": 4.0647783279418945, | |
| "learning_rate": 4.5421760615808474e-05, | |
| "loss": 2.1589, | |
| "num_input_tokens_seen": 1771664, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.2064090480678604, | |
| "grad_norm": 3.4753596782684326, | |
| "learning_rate": 4.513175643827647e-05, | |
| "loss": 2.0505, | |
| "num_input_tokens_seen": 1829824, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.244109330819981, | |
| "grad_norm": 3.573631525039673, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 2.0924, | |
| "num_input_tokens_seen": 1882384, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2818096135721018, | |
| "grad_norm": 3.39180588722229, | |
| "learning_rate": 4.4528109009727336e-05, | |
| "loss": 2.0184, | |
| "num_input_tokens_seen": 1939456, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3195098963242224, | |
| "grad_norm": 4.136682987213135, | |
| "learning_rate": 4.42147032012394e-05, | |
| "loss": 2.1524, | |
| "num_input_tokens_seen": 1996320, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3572101790763431, | |
| "grad_norm": 3.9565956592559814, | |
| "learning_rate": 4.389373935885646e-05, | |
| "loss": 2.1253, | |
| "num_input_tokens_seen": 2056560, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3949104618284638, | |
| "grad_norm": 3.7363975048065186, | |
| "learning_rate": 4.356534373254316e-05, | |
| "loss": 2.0752, | |
| "num_input_tokens_seen": 2118496, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4326107445805842, | |
| "grad_norm": 4.311358451843262, | |
| "learning_rate": 4.322964549552943e-05, | |
| "loss": 2.0574, | |
| "num_input_tokens_seen": 2178352, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4703110273327051, | |
| "grad_norm": 3.684499502182007, | |
| "learning_rate": 4.288677669350066e-05, | |
| "loss": 2.0481, | |
| "num_input_tokens_seen": 2233440, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.5080113100848256, | |
| "grad_norm": 4.71754264831543, | |
| "learning_rate": 4.2536872192658036e-05, | |
| "loss": 2.0859, | |
| "num_input_tokens_seen": 2289648, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5457115928369463, | |
| "grad_norm": 4.160897731781006, | |
| "learning_rate": 4.218006962666934e-05, | |
| "loss": 2.0877, | |
| "num_input_tokens_seen": 2346224, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.583411875589067, | |
| "grad_norm": 3.895419120788574, | |
| "learning_rate": 4.181650934253132e-05, | |
| "loss": 2.0488, | |
| "num_input_tokens_seen": 2407392, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.6211121583411876, | |
| "grad_norm": 4.271753787994385, | |
| "learning_rate": 4.144633434536467e-05, | |
| "loss": 2.0074, | |
| "num_input_tokens_seen": 2462400, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6588124410933083, | |
| "grad_norm": 4.415102958679199, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 2.0844, | |
| "num_input_tokens_seen": 2518304, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6965127238454287, | |
| "grad_norm": 4.525811672210693, | |
| "learning_rate": 4.06867251845213e-05, | |
| "loss": 2.0943, | |
| "num_input_tokens_seen": 2583168, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7342130065975496, | |
| "grad_norm": 4.545309543609619, | |
| "learning_rate": 4.0297589810356165e-05, | |
| "loss": 2.0858, | |
| "num_input_tokens_seen": 2643552, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.77191328934967, | |
| "grad_norm": 4.468845844268799, | |
| "learning_rate": 3.9902437184657784e-05, | |
| "loss": 2.044, | |
| "num_input_tokens_seen": 2705600, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.8096135721017907, | |
| "grad_norm": 4.4386138916015625, | |
| "learning_rate": 3.9501422739279956e-05, | |
| "loss": 2.1083, | |
| "num_input_tokens_seen": 2765856, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.8473138548539114, | |
| "grad_norm": 3.7564873695373535, | |
| "learning_rate": 3.909470421180201e-05, | |
| "loss": 2.0431, | |
| "num_input_tokens_seen": 2824192, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.885014137606032, | |
| "grad_norm": 4.3798418045043945, | |
| "learning_rate": 3.8682441583483314e-05, | |
| "loss": 2.0978, | |
| "num_input_tokens_seen": 2880208, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9227144203581528, | |
| "grad_norm": 4.044529914855957, | |
| "learning_rate": 3.8264797016335205e-05, | |
| "loss": 2.096, | |
| "num_input_tokens_seen": 2939856, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.9604147031102732, | |
| "grad_norm": 4.19630241394043, | |
| "learning_rate": 3.7841934789335164e-05, | |
| "loss": 1.9965, | |
| "num_input_tokens_seen": 2995552, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.998114985862394, | |
| "grad_norm": 4.908398151397705, | |
| "learning_rate": 3.741402123380828e-05, | |
| "loss": 2.1569, | |
| "num_input_tokens_seen": 3055504, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.0358152686145146, | |
| "grad_norm": 4.20371150970459, | |
| "learning_rate": 3.6981224668001424e-05, | |
| "loss": 1.7904, | |
| "num_input_tokens_seen": 3110576, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0735155513666355, | |
| "grad_norm": 5.414203643798828, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 1.7416, | |
| "num_input_tokens_seen": 3171440, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.111215834118756, | |
| "grad_norm": 5.226822853088379, | |
| "learning_rate": 3.610166531514436e-05, | |
| "loss": 1.7513, | |
| "num_input_tokens_seen": 3219792, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.1489161168708764, | |
| "grad_norm": 5.410066604614258, | |
| "learning_rate": 3.565524849957921e-05, | |
| "loss": 1.7565, | |
| "num_input_tokens_seen": 3275792, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.1866163996229973, | |
| "grad_norm": 5.878467082977295, | |
| "learning_rate": 3.520464048061758e-05, | |
| "loss": 1.7417, | |
| "num_input_tokens_seen": 3333136, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.2243166823751177, | |
| "grad_norm": 5.918631553649902, | |
| "learning_rate": 3.47500185032913e-05, | |
| "loss": 1.7726, | |
| "num_input_tokens_seen": 3390080, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.2620169651272386, | |
| "grad_norm": 6.060715675354004, | |
| "learning_rate": 3.4291561391508185e-05, | |
| "loss": 1.7763, | |
| "num_input_tokens_seen": 3446208, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.299717247879359, | |
| "grad_norm": 6.188582897186279, | |
| "learning_rate": 3.3829449477712324e-05, | |
| "loss": 1.7327, | |
| "num_input_tokens_seen": 3508240, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.3374175306314795, | |
| "grad_norm": 6.416080951690674, | |
| "learning_rate": 3.336386453195088e-05, | |
| "loss": 1.7441, | |
| "num_input_tokens_seen": 3569856, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.3751178133836004, | |
| "grad_norm": 6.098644733428955, | |
| "learning_rate": 3.2894989690375626e-05, | |
| "loss": 1.7355, | |
| "num_input_tokens_seen": 3631984, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.412818096135721, | |
| "grad_norm": 7.12858772277832, | |
| "learning_rate": 3.2423009383206876e-05, | |
| "loss": 1.7182, | |
| "num_input_tokens_seen": 3688192, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.4505183788878417, | |
| "grad_norm": 6.329550266265869, | |
| "learning_rate": 3.194810926218861e-05, | |
| "loss": 1.7332, | |
| "num_input_tokens_seen": 3746720, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.488218661639962, | |
| "grad_norm": 6.534445762634277, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 1.6908, | |
| "num_input_tokens_seen": 3802432, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.525918944392083, | |
| "grad_norm": 6.304942607879639, | |
| "learning_rate": 3.099029785459328e-05, | |
| "loss": 1.7756, | |
| "num_input_tokens_seen": 3856800, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.5636192271442035, | |
| "grad_norm": 6.389725208282471, | |
| "learning_rate": 3.0507763319663517e-05, | |
| "loss": 1.7737, | |
| "num_input_tokens_seen": 3916320, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.6013195098963244, | |
| "grad_norm": 6.7536940574646, | |
| "learning_rate": 3.002306232598497e-05, | |
| "loss": 1.7446, | |
| "num_input_tokens_seen": 3974864, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.639019792648445, | |
| "grad_norm": 6.574880599975586, | |
| "learning_rate": 2.9536385528937567e-05, | |
| "loss": 1.7283, | |
| "num_input_tokens_seen": 4032656, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.6767200754005653, | |
| "grad_norm": 5.760074138641357, | |
| "learning_rate": 2.9047924361076345e-05, | |
| "loss": 1.7573, | |
| "num_input_tokens_seen": 4092800, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.7144203581526862, | |
| "grad_norm": 6.087067604064941, | |
| "learning_rate": 2.8557870956832132e-05, | |
| "loss": 1.6758, | |
| "num_input_tokens_seen": 4144592, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.7521206409048067, | |
| "grad_norm": 7.485050201416016, | |
| "learning_rate": 2.8066418076936167e-05, | |
| "loss": 1.7087, | |
| "num_input_tokens_seen": 4200000, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.7898209236569276, | |
| "grad_norm": 7.791069984436035, | |
| "learning_rate": 2.7573759032598366e-05, | |
| "loss": 1.7527, | |
| "num_input_tokens_seen": 4262288, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.827521206409048, | |
| "grad_norm": 6.225643634796143, | |
| "learning_rate": 2.7080087609469062e-05, | |
| "loss": 1.786, | |
| "num_input_tokens_seen": 4317040, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.8652214891611685, | |
| "grad_norm": 5.990758895874023, | |
| "learning_rate": 2.6585597991414114e-05, | |
| "loss": 1.677, | |
| "num_input_tokens_seen": 4376576, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.9029217719132894, | |
| "grad_norm": 6.876400470733643, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 1.7027, | |
| "num_input_tokens_seen": 4429024, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.9406220546654103, | |
| "grad_norm": 6.724515914916992, | |
| "learning_rate": 2.5594942438652688e-05, | |
| "loss": 1.7717, | |
| "num_input_tokens_seen": 4494400, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.9783223374175307, | |
| "grad_norm": 7.128418922424316, | |
| "learning_rate": 2.509916617471903e-05, | |
| "loss": 1.8441, | |
| "num_input_tokens_seen": 4554576, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.016022620169651, | |
| "grad_norm": 5.73885440826416, | |
| "learning_rate": 2.46033509041298e-05, | |
| "loss": 1.604, | |
| "num_input_tokens_seen": 4612352, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 792, | |
| "num_input_tokens_seen": 4612352, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.973615717420892e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |